6 papers
Frozen in a Frame: The Velocity Blind Spot in JEPA World Models
Tinghe Zhang, Chunyu Liu, Yu Leon Liu +6
Joint-embedding predictive architectures (JEPAs) for world modeling train an encoder so a predictor maps a current embedding and action to the next frame's embedding, always from a…
Effective Does Not Mean Useful: Conditional Functional Substitutability for Redundancy and Scaling in Transformers
Jiaheng Chen, Jiaxing Li, Yucheng Xiao +4
Modern neural networks scale predictably, yet the mechanisms behind these regularities remain unclear. Neural redundancy is typically characterized by component importance or repre…
GEAR: From Dynamic Encoding to Dynamic Activation in Social Trajectory Prediction
Jiaheng Chen, Jiaxing Li, Leixia Wang +2
Human trajectory prediction requires modeling both individual motion patterns and social interactions among agents. Existing methods have made substantial progress by using attenti…
A Unified Framework for Trajectory Prediction with Explicit Planning and Reaction Decomposition
Jiaheng Chen, Jiaxing Li, Tinghe Zhang +1
Trajectory prediction has shifted toward structured formulations with explicit social modeling. However, existing methods inadequately distinguish the functional roles of social in…
NodeJEPA: Structure-Conditioned Latent Prediction for Node-Level Graph Self-Supervised Learning
Tinghe Zhang, Jian Xu, Jiaheng Chen +3
Self-supervised learning on graphs is largely shaped by contrastive methods that depend on carefully designed augmentations, and by generative methods that reconstruct node attribu…
Boosting Single Positive Multi-label Classification with Generalized Robust Loss
Yanxi Chen, Chunxiao Li, Xinyang Dai +6
Multi-label learning (MLL) requires comprehensive multi-semantic annotations that is hard to fully obtain, thus often resulting in missing labels scenarios. In this paper, we inves…